University of Magdalena

Nonlinear Modeling for the Construction of a Synthetic Index: An Approach Based on UMAP and Random Forest Applied to the Energy Performance of OECD Countries

This article proposes a hybrid method for constructing composite indices in the context of decision-making through the integration of Uniform Manifold Approximation and Projection (UMAP) and the Random Forest algorithm. Unlike Principal Component Analysis (PCA) and the Analytic H...

Spatial Data Fusion and Machine Learning Bias Correction for Convection-Permitting Atmospheric Downscaling and Multi-Criteria Site Feasibility Mapping in Complex Coastal Terrains

High-resolution atmospheric modeling over topographically complex coastal zones requires multi-source spatial data fusion to bridge the scale gap between satellite-assimilated global reanalysis and localized boundary layer dynamics. This study presents a spatial data fusion frame...

The first annotated checklist of the bees of Colombia reveals an overlooked diversity and areas with major data deficiencies

Background Most existing knowledge about bee biodiversity comes from temperate regions, where diversity is presumed highest—yet substantial data gaps across the tropics confound this pattern. Checklists are critical for documenting species presence, identifying knowledge gaps, an...

Edge-Optimized Reservoir Computing for Forecasting Complex Ecological Systems: Predicting Fishery Collapse with Incomplete Data

Monitoring landings in data-scarce fisheries is hampered by short, noisy series and multi-year reporting gaps. We benchmark Echo State Networks (ESNs) against SARIMA, LightGBM, and LSTM models and against naïve and seasonal-naïve persistence, for one-step-ahead forecasting of the...

A Scientometric Study of Usability and User Experience Evaluation: Evolution, Context and Trends

Usability and user experience (UX) evaluation frameworks are well established within human–computer interaction and human factors research, yet they are typically applied as general-purpose models that do not fully capture the specific cognitive and perceptual demands of open dat...

Skewed Criterion-Weight Distributions for Spatially Regularized Selection of IoT-Enabled Environmental Monitoring Nodes

This work presents a spatially regularized modelling framework for selecting IoT-enabled environmental monitoring nodes within smart-lighting infrastructures. The study does not claim novelty in CRITIC, TOPSIS, mixed-integer programming, or Voronoi tessellation as isolated method...